TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Adaptive Inference Using Hierarchical Convolutional Bag-of-Features for Low-Power Embedded Platforms

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2019 IEEE International Conference on Image Processing (ICIP)
KustantajaIEEE
Sivut3048-3052
Sivumäärä5
ISBN (elektroninen)978-1-5386-6249-6
ISBN (painettu)978-1-5386-6250-2
DOI - pysyväislinkit
TilaJulkaistu - syyskuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING -
Kesto: 1 tammikuuta 1900 → …

Julkaisusarja

NimiIEEE International Conference on Image Processing
ISSN (painettu)1522-4880
ISSN (elektroninen)2381-8549

Conference

ConferenceIEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
Ajanjakso1/01/00 → …

Tiivistelmä

Using early exits provide a straightforward way to implement models that can adapt on-the-fly to the available computational resources. However, early exits in many cases suffer from significant limitations, which often prohibit their practical application, especially when placed on convolutional layers with narrow receptive fields. In this work, we propose a method capable of overcoming these limitations by a) using a Bag-of-Features (BoF)-based pooling approach, that allows for keeping more information regarding the distribution of the extracted feature vectors, while also maintaining more spatial information and b) employing a simple, yet effective, hierarchical approach for designing the exits, allowing for efficiently re-using the information that was already extracted by the previous layers. It is experimentally demonstrated that the proposed approach leads to significant performance improvements, allowing early exits to be a more practical tool that can be used in many real-world embedded applications.

Tutkimusalat

Julkaisufoorumi-taso